Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/rzhang/linux

Pull thermal updates from Zhang Rui:

 - Implement generic devfreq cooling mechanism through frequency
   reduction for devices using devfreq.  From Ørjan Eide and Javi
   Merino.

 - Introduce OMAP3 support on TI SoC thermal driver.  From Pavel Mack
   and Eduardo Valentin.

 - A bounch of small fixes on devfreq_cooling, Exynos, IMX, Armada, and
   Rockchip thermal drivers.

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/rzhang/linux: (24 commits)
  thermal: exynos: Directly return 0 instead of using local ret variable
  thermal: exynos: Remove unneeded semicolon
  thermal: exynos: Use IS_ERR() because regulator cannot be NULL
  thermal: exynos: Fix first temperature read after registering sensor
  thermal: exynos: Fix unbalanced regulator disable on probe failure
  devfreq_cooling: return on allocation failure
  thermal: rockchip: support the sleep pinctrl state to avoid glitches in s2r
  dt-bindings: rockchip-thermal: Add the pinctrl states in this document
  thermal: devfreq_cooling: Make power a u64
  thermal: devfreq_cooling: use a thermal_cooling_device for register and unregister
  thermal: underflow bug in imx_set_trip_temp()
  thermal: armada: Fix possible overflow in the Armada 380 thermal sensor formula
  thermal: imx: register irq handler later in probe
  thermal: rockhip: fix setting thermal shutdown polarity
  thermal: rockchip: fix handling of invalid readings
  devfreq_cooling: add trace information
  thermal: Add devfreq cooling
  PM / OPP: get the voltage for all OPPs
  tools/thermal: tmon: use pkg-config also for CFLAGS
  linux/thermal.h: rename KELVIN_TO_CELSIUS to DECI_KELVIN_TO_CELSIUS
  ...

23 files changed, 1065 insertions, 86 deletions

diff --git a/Documentation/devicetree/bindings/thermal/rockchip-thermal.txt b/Documentation/devicetree/bindings/thermal/rockchip-thermal.txt
index ef802de4957a..b38200d2583a 100644
--- a/Documentation/devicetree/bindings/thermal/rockchip-thermal.txt
+++ b/Documentation/devicetree/bindings/thermal/rockchip-thermal.txt
@@ -12,6 +12,11 @@ Required properties:
 - resets : Must contain an entry for each entry in reset-names.
 	   See ../reset/reset.txt for details.
 - reset-names : Must include the name "tsadc-apb".
+- pinctrl-names : The pin control state names;
+- pinctrl-0 : The "init" pinctrl state, it will be set before device probe.
+- pinctrl-1 : The "default" pinctrl state, it will be set after reset the
+	      TSADC controller.
+- pinctrl-2 : The "sleep" pinctrl state, it will be in for suspend.
 - #thermal-sensor-cells : Should be 1. See ./thermal.txt for a description.
 - rockchip,hw-tshut-temp : The hardware-controlled shutdown temperature value.
 - rockchip,hw-tshut-mode : The hardware-controlled shutdown mode 0:CRU 1:GPIO.
@@ -27,8 +32,10 @@ tsadc: tsadc@ff280000 {
 	clock-names = "tsadc", "apb_pclk";
 	resets = <&cru SRST_TSADC>;
 	reset-names = "tsadc-apb";
-	pinctrl-names = "default";
-	pinctrl-0 = <&otp_out>;
+	pinctrl-names = "init", "default", "sleep";
+	pinctrl-0 = <&otp_gpio>;
+	pinctrl-1 = <&otp_out>;
+	pinctrl-2 = <&otp_gpio>;
 	#thermal-sensor-cells = <1>;
 	rockchip,hw-tshut-temp = <95000>;
 	rockchip,hw-tshut-mode = <0>;
diff --git a/Documentation/devicetree/bindings/thermal/ti_soc_thermal.txt b/Documentation/devicetree/bindings/thermal/ti_soc_thermal.txt
index 0c9222d27fae..6299dd8de339 100644
--- a/Documentation/devicetree/bindings/thermal/ti_soc_thermal.txt
+++ b/Documentation/devicetree/bindings/thermal/ti_soc_thermal.txt
@@ -10,6 +10,8 @@ to the silicon temperature.
 
 Required properties:
 - compatible : Should be:
+  - "ti,omap34xx-bandgap" : for OMAP34xx bandgap
+  - "ti,omap36xx-bandgap" : for OMAP36xx bandgap
   - "ti,omap4430-bandgap" : for OMAP4430 bandgap
   - "ti,omap4460-bandgap" : for OMAP4460 bandgap
   - "ti,omap4470-bandgap" : for OMAP4470 bandgap
@@ -25,6 +27,18 @@ to each bandgap version, because the mapping may change from
 soc to soc, apart of depending on available features.
 
 Example:
+OMAP34xx:
+bandgap {
+	reg = <0x48002524 0x4>;
+	compatible = "ti,omap34xx-bandgap";
+};
+
+OMAP36xx:
+bandgap {
+	reg = <0x48002524 0x4>;
+	compatible = "ti,omap36xx-bandgap";
+};
+
 OMAP4430:
 bandgap {
 	reg = <0x4a002260 0x4 0x4a00232C 0x4>;
diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c
index 30d8518b25fb..82707f9824ca 100644
--- a/drivers/acpi/thermal.c
+++ b/drivers/acpi/thermal.c
@@ -315,7 +315,7 @@ static int acpi_thermal_trips_update(struct acpi_thermal *tz, int flag)
 			if (crt == -1) {
 				tz->trips.critical.flags.valid = 0;
 			} else if (crt > 0) {
-				unsigned long crt_k = CELSIUS_TO_KELVIN(crt);
+				unsigned long crt_k = CELSIUS_TO_DECI_KELVIN(crt);
 				/*
 				 * Allow override critical threshold
 				 */
@@ -351,7 +351,7 @@ static int acpi_thermal_trips_update(struct acpi_thermal *tz, int flag)
 		if (psv == -1) {
 			status = AE_SUPPORT;
 		} else if (psv > 0) {
-			tmp = CELSIUS_TO_KELVIN(psv);
+			tmp = CELSIUS_TO_DECI_KELVIN(psv);
 			status = AE_OK;
 		} else {
 			status = acpi_evaluate_integer(tz->device->handle,
@@ -431,7 +431,7 @@ static int acpi_thermal_trips_update(struct acpi_thermal *tz, int flag)
 					break;
 				if (i == 1)
 					tz->trips.active[0].temperature =
-						CELSIUS_TO_KELVIN(act);
+						CELSIUS_TO_DECI_KELVIN(act);
 				else
 					/*
 					 * Don't allow override higher than
@@ -439,9 +439,9 @@ static int acpi_thermal_trips_update(struct acpi_thermal *tz, int flag)
 					 */
 					tz->trips.active[i - 1].temperature =
 						(tz->trips.active[i - 2].temperature <
-						CELSIUS_TO_KELVIN(act) ?
+						CELSIUS_TO_DECI_KELVIN(act) ?
 						tz->trips.active[i - 2].temperature :
-						CELSIUS_TO_KELVIN(act));
+						CELSIUS_TO_DECI_KELVIN(act));
 				break;
 			} else {
 				tz->trips.active[i].temperature = tmp;
@@ -1105,7 +1105,7 @@ static int acpi_thermal_add(struct acpi_device *device)
 	INIT_WORK(&tz->thermal_check_work, acpi_thermal_check_fn);
 
 	pr_info(PREFIX "%s [%s] (%ld C)\n", acpi_device_name(device),
-		acpi_device_bid(device), KELVIN_TO_CELSIUS(tz->temperature));
+		acpi_device_bid(device), DECI_KELVIN_TO_CELSIUS(tz->temperature));
 	goto end;
 
 free_memory:
diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c
index d5c1149ff123..270902007055 100644
--- a/drivers/base/power/opp/core.c
+++ b/drivers/base/power/opp/core.c
@@ -100,7 +100,7 @@ struct device_opp *_find_device_opp(struct device *dev)
 }
 
 /**
- * dev_pm_opp_get_voltage() - Gets the voltage corresponding to an available opp
+ * dev_pm_opp_get_voltage() - Gets the voltage corresponding to an opp
  * @opp:	opp for which voltage has to be returned for
  *
  * Return: voltage in micro volt corresponding to the opp, else
@@ -122,7 +122,7 @@ unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp)
 	opp_rcu_lockdep_assert();
 
 	tmp_opp = rcu_dereference(opp);
-	if (IS_ERR_OR_NULL(tmp_opp) || !tmp_opp->available)
+	if (IS_ERR_OR_NULL(tmp_opp))
 		pr_err("%s: Invalid parameters\n", __func__);
 	else
 		v = tmp_opp->u_volt;
diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
index 1f7d80ff8cb4..e3a750224ae2 100644
--- a/drivers/platform/x86/asus-wmi.c
+++ b/drivers/platform/x86/asus-wmi.c
@@ -1320,7 +1320,7 @@ static ssize_t asus_hwmon_temp1(struct device *dev,
 	if (err < 0)
 		return err;
 
-	value = KELVIN_TO_CELSIUS((value & 0xFFFF)) * 1000;
+	value = DECI_KELVIN_TO_CELSIUS((value & 0xFFFF)) * 1000;
 
 	return sprintf(buf, "%d\n", value);
 }
diff --git a/drivers/platform/x86/intel_menlow.c b/drivers/platform/x86/intel_menlow.c
index e8b46d2c468c..0a919d81662c 100644
--- a/drivers/platform/x86/intel_menlow.c
+++ b/drivers/platform/x86/intel_menlow.c
@@ -315,7 +315,7 @@ static ssize_t aux0_show(struct device *dev,
 
 	result = sensor_get_auxtrip(attr->handle, 0, &value);
 
-	return result ? result : sprintf(buf, "%lu", KELVIN_TO_CELSIUS(value));
+	return result ? result : sprintf(buf, "%lu", DECI_KELVIN_TO_CELSIUS(value));
 }
 
 static ssize_t aux1_show(struct device *dev,
@@ -327,7 +327,7 @@ static ssize_t aux1_show(struct device *dev,
 
 	result = sensor_get_auxtrip(attr->handle, 1, &value);
 
-	return result ? result : sprintf(buf, "%lu", KELVIN_TO_CELSIUS(value));
+	return result ? result : sprintf(buf, "%lu", DECI_KELVIN_TO_CELSIUS(value));
 }
 
 static ssize_t aux0_store(struct device *dev,
@@ -345,7 +345,7 @@ static ssize_t aux0_store(struct device *dev,
 	if (value < 0)
 		return -EINVAL;
 
-	result = sensor_set_auxtrip(attr->handle, 0, CELSIUS_TO_KELVIN(value));
+	result = sensor_set_auxtrip(attr->handle, 0, CELSIUS_TO_DECI_KELVIN(value));
 	return result ? result : count;
 }
 
@@ -364,7 +364,7 @@ static ssize_t aux1_store(struct device *dev,
 	if (value < 0)
 		return -EINVAL;
 
-	result = sensor_set_auxtrip(attr->handle, 1, CELSIUS_TO_KELVIN(value));
+	result = sensor_set_auxtrip(attr->handle, 1, CELSIUS_TO_DECI_KELVIN(value));
 	return result ? result : count;
 }
 
diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig
index 5aabc4bc0d75..c463c89b90ef 100644
--- a/drivers/thermal/Kconfig
+++ b/drivers/thermal/Kconfig
@@ -147,6 +147,20 @@ config CLOCK_THERMAL
 	  device that is configured to use this cooling mechanism will be
 	  controlled to reduce clock frequency whenever temperature is high.
 
+config DEVFREQ_THERMAL
+	bool "Generic device cooling support"
+	depends on PM_DEVFREQ
+	depends on PM_OPP
+	help
+	  This implements the generic devfreq cooling mechanism through
+	  frequency reduction for devices using devfreq.
+
+	  This will throttle the device by limiting the maximum allowed DVFS
+	  frequency corresponding to the cooling level.
+
+	  In order to use the power extensions of the cooling device,
+	  devfreq should use the simple_ondemand governor.
+
 	  If you want this support, you should say Y here.
 
 config THERMAL_EMULATION
@@ -275,6 +289,7 @@ config X86_PKG_TEMP_THERMAL
 	tristate "X86 package temperature thermal driver"
 	depends on X86_THERMAL_VECTOR
 	select THERMAL_GOV_USER_SPACE
+	select THERMAL_WRITABLE_TRIPS
 	default m
 	help
 	  Enable this to register CPU digital sensor for package temperature as
@@ -296,6 +311,7 @@ config INTEL_SOC_DTS_THERMAL
 	tristate "Intel SoCs DTS thermal driver"
 	depends on X86
 	select INTEL_SOC_DTS_IOSF_CORE
+	select THERMAL_WRITABLE_TRIPS
 	help
 	  Enable this to register Intel SoCs (e.g. Bay Trail) platform digital
 	  temperature sensor (DTS). These SoCs have two additional DTSs in
@@ -322,6 +338,7 @@ config INT340X_THERMAL
 	select ACPI_THERMAL_REL
 	select ACPI_FAN
 	select INTEL_SOC_DTS_IOSF_CORE
+	select THERMAL_WRITABLE_TRIPS
 	help
 	  Newer laptops and tablets that use ACPI may have thermal sensors and
 	  other devices with thermal control capabilities outside the core
diff --git a/drivers/thermal/Makefile b/drivers/thermal/Makefile
index 26f160809959..cfae6a654793 100644
--- a/drivers/thermal/Makefile
+++ b/drivers/thermal/Makefile
@@ -22,6 +22,9 @@ thermal_sys-$(CONFIG_CPU_THERMAL)	+= cpu_cooling.o
 # clock cooling
 thermal_sys-$(CONFIG_CLOCK_THERMAL)	+= clock_cooling.o
 
+# devfreq cooling
+thermal_sys-$(CONFIG_DEVFREQ_THERMAL) += devfreq_cooling.o
+
 # platform thermal drivers
 obj-$(CONFIG_QCOM_SPMI_TEMP_ALARM)	+= qcom-spmi-temp-alarm.o
 obj-$(CONFIG_SPEAR_THERMAL)	+= spear_thermal.o
diff --git a/drivers/thermal/armada_thermal.c b/drivers/thermal/armada_thermal.c
index 26b8d326546a..ae75328945f7 100644
--- a/drivers/thermal/armada_thermal.c
+++ b/drivers/thermal/armada_thermal.c
@@ -224,9 +224,9 @@ static const struct armada_thermal_data armada380_data = {
 	.is_valid_shift = 10,
 	.temp_shift = 0,
 	.temp_mask = 0x3ff,
-	.coef_b = 2931108200UL,
-	.coef_m = 5000000UL,
-	.coef_div = 10502,
+	.coef_b = 1172499100UL,
+	.coef_m = 2000096UL,
+	.coef_div = 4201,
 	.inverted = true,
 };
 
diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index 42c6f71bdcc1..e3fbc5a5d88f 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -591,8 +591,7 @@ static int cpufreq_get_requested_power(struct thermal_cooling_device *cdev,
 	if (trace_thermal_power_cpu_get_power_enabled()) {
 		u32 ncpus = cpumask_weight(&cpufreq_device->allowed_cpus);
 
-		load_cpu = devm_kcalloc(&cdev->device, ncpus, sizeof(*load_cpu),
-					GFP_KERNEL);
+		load_cpu = kcalloc(ncpus, sizeof(*load_cpu), GFP_KERNEL);
 	}
 
 	for_each_cpu(cpu, &cpufreq_device->allowed_cpus) {
@@ -615,8 +614,7 @@ static int cpufreq_get_requested_power(struct thermal_cooling_device *cdev,
 	dynamic_power = get_dynamic_power(cpufreq_device, freq);
 	ret = get_static_power(cpufreq_device, tz, freq, &static_power);
 	if (ret) {
-		if (load_cpu)
-			devm_kfree(&cdev->device, load_cpu);
+		kfree(load_cpu);
 		return ret;
 	}
 
@@ -625,7 +623,7 @@ static int cpufreq_get_requested_power(struct thermal_cooling_device *cdev,
 			&cpufreq_device->allowed_cpus,
 			freq, load_cpu, i, dynamic_power, static_power);
 
-		devm_kfree(&cdev->device, load_cpu);
+		kfree(load_cpu);
 	}
 
 	*power = static_power + dynamic_power;
diff --git a/drivers/thermal/devfreq_cooling.c b/drivers/thermal/devfreq_cooling.c
new file mode 100644
index 000000000000..01f0015f80dc
--- /dev/null
+++ b/drivers/thermal/devfreq_cooling.c
@@ -0,0 +1,573 @@
+/*
+ * devfreq_cooling: Thermal cooling device implementation for devices using
+ *                  devfreq
+ *
+ * Copyright (C) 2014-2015 ARM Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * TODO:
+ *    - If OPPs are added or removed after devfreq cooling has
+ *      registered, the devfreq cooling won't react to it.
+ */
+
+#include <linux/devfreq.h>
+#include <linux/devfreq_cooling.h>
+#include <linux/export.h>
+#include <linux/slab.h>
+#include <linux/pm_opp.h>
+#include <linux/thermal.h>
+
+#include <trace/events/thermal.h>
+
+static DEFINE_MUTEX(devfreq_lock);
+static DEFINE_IDR(devfreq_idr);
+
+/**
+ * struct devfreq_cooling_device - Devfreq cooling device
+ * @id:		unique integer value corresponding to each
+ *		devfreq_cooling_device registered.
+ * @cdev:	Pointer to associated thermal cooling device.
+ * @devfreq:	Pointer to associated devfreq device.
+ * @cooling_state:	Current cooling state.
+ * @power_table:	Pointer to table with maximum power draw for each
+ *			cooling state. State is the index into the table, and
+ *			the power is in mW.
+ * @freq_table:	Pointer to a table with the frequencies sorted in descending
+ *		order.  You can index the table by cooling device state
+ * @freq_table_size:	Size of the @freq_table and @power_table
+ * @power_ops:	Pointer to devfreq_cooling_power, used to generate the
+ *		@power_table.
+ */
+struct devfreq_cooling_device {
+	int id;
+	struct thermal_cooling_device *cdev;
+	struct devfreq *devfreq;
+	unsigned long cooling_state;
+	u32 *power_table;
+	u32 *freq_table;
+	size_t freq_table_size;
+	struct devfreq_cooling_power *power_ops;
+};
+
+/**
+ * get_idr - function to get a unique id.
+ * @idr: struct idr * handle used to create a id.
+ * @id: int * value generated by this function.
+ *
+ * This function will populate @id with an unique
+ * id, using the idr API.
+ *
+ * Return: 0 on success, an error code on failure.
+ */
+static int get_idr(struct idr *idr, int *id)
+{
+	int ret;
+
+	mutex_lock(&devfreq_lock);
+	ret = idr_alloc(idr, NULL, 0, 0, GFP_KERNEL);
+	mutex_unlock(&devfreq_lock);
+	if (unlikely(ret < 0))
+		return ret;
+	*id = ret;
+
+	return 0;
+}
+
+/**
+ * release_idr - function to free the unique id.
+ * @idr: struct idr * handle used for creating the id.
+ * @id: int value representing the unique id.
+ */
+static void release_idr(struct idr *idr, int id)
+{
+	mutex_lock(&devfreq_lock);
+	idr_remove(idr, id);
+	mutex_unlock(&devfreq_lock);
+}
+
+/**
+ * partition_enable_opps() - disable all opps above a given state
+ * @dfc:	Pointer to devfreq we are operating on
+ * @cdev_state:	cooling device state we're setting
+ *
+ * Go through the OPPs of the device, enabling all OPPs until
+ * @cdev_state and disabling those frequencies above it.
+ */
+static int partition_enable_opps(struct devfreq_cooling_device *dfc,
+				 unsigned long cdev_state)
+{
+	int i;
+	struct device *dev = dfc->devfreq->dev.parent;
+
+	for (i = 0; i < dfc->freq_table_size; i++) {
+		struct dev_pm_opp *opp;
+		int ret = 0;
+		unsigned int freq = dfc->freq_table[i];
+		bool want_enable = i >= cdev_state ? true : false;
+
+		rcu_read_lock();
+		opp = dev_pm_opp_find_freq_exact(dev, freq, !want_enable);
+		rcu_read_unlock();
+
+		if (PTR_ERR(opp) == -ERANGE)
+			continue;
+		else if (IS_ERR(opp))
+			return PTR_ERR(opp);
+
+		if (want_enable)
+			ret = dev_pm_opp_enable(dev, freq);
+		else
+			ret = dev_pm_opp_disable(dev, freq);
+
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int devfreq_cooling_get_max_state(struct thermal_cooling_device *cdev,
+					 unsigned long *state)
+{
+	struct devfreq_cooling_device *dfc = cdev->devdata;
+
+	*state = dfc->freq_table_size - 1;
+
+	return 0;
+}
+
+static int devfreq_cooling_get_cur_state(struct thermal_cooling_device *cdev,
+					 unsigned long *state)
+{
+	struct devfreq_cooling_device *dfc = cdev->devdata;
+
+	*state = dfc->cooling_state;
+
+	return 0;
+}
+
+static int devfreq_cooling_set_cur_state(struct thermal_cooling_device *cdev,
+					 unsigned long state)
+{
+	struct devfreq_cooling_device *dfc = cdev->devdata;
+	struct devfreq *df = dfc->devfreq;
+	struct device *dev = df->dev.parent;
+	int ret;
+
+	if (state == dfc->cooling_state)
+		return 0;
+
+	dev_dbg(dev, "Setting cooling state %lu\n", state);
+
+	if (state >= dfc->freq_table_size)
+		return -EINVAL;
+
+	ret = partition_enable_opps(dfc, state);
+	if (ret)
+		return ret;
+
+	dfc->cooling_state = state;
+
+	return 0;
+}
+
+/**
+ * freq_get_state() - get the cooling state corresponding to a frequency
+ * @dfc:	Pointer to devfreq cooling device
+ * @freq:	frequency in Hz
+ *
+ * Return: the cooling state associated with the @freq, or
+ * THERMAL_CSTATE_INVALID if it wasn't found.
+ */
+static unsigned long
+freq_get_state(struct devfreq_cooling_device *dfc, unsigned long freq)
+{
+	int i;
+
+	for (i = 0; i < dfc->freq_table_size; i++) {
+		if (dfc->freq_table[i] == freq)
+			return i;
+	}
+
+	return THERMAL_CSTATE_INVALID;
+}
+
+/**
+ * get_static_power() - calculate the static power
+ * @dfc:	Pointer to devfreq cooling device
+ * @freq:	Frequency in Hz
+ *
+ * Calculate the static power in milliwatts using the supplied
+ * get_static_power().  The current voltage is calculated using the
+ * OPP library.  If no get_static_power() was supplied, assume the
+ * static power is negligible.
+ */
+static unsigned long
+get_static_power(struct devfreq_cooling_device *dfc, unsigned long freq)
+{
+	struct devfreq *df = dfc->devfreq;
+	struct device *dev = df->dev.parent;
+	unsigned long voltage;
+	struct dev_pm_opp *opp;
+
+	if (!dfc->power_ops->get_static_power)
+		return 0;
+
+	rcu_read_lock();
+
+	opp = dev_pm_opp_find_freq_exact(dev, freq, true);
+	if (IS_ERR(opp) && (PTR_ERR(opp) == -ERANGE))
+		opp = dev_pm_opp_find_freq_exact(dev, freq, false);
+
+	voltage = dev_pm_opp_get_voltage(opp) / 1000; /* mV */
+
+	rcu_read_unlock();
+
+	if (voltage == 0) {
+		dev_warn_ratelimited(dev,
+				     "Failed to get voltage for frequency %lu: %ld\n",
+				     freq, IS_ERR(opp) ? PTR_ERR(opp) : 0);
+		return 0;
+	}
+
+	return dfc->power_ops->get_static_power(voltage);
+}
+
+/**
+ * get_dynamic_power - calculate the dynamic power
+ * @dfc:	Pointer to devfreq cooling device
+ * @freq:	Frequency in Hz
+ * @voltage:	Voltage in millivolts
+ *
+ * Calculate the dynamic power in milliwatts consumed by the device at
+ * frequency @freq and voltage @voltage.  If the get_dynamic_power()
+ * was supplied as part of the devfreq_cooling_power struct, then that
+ * function is used.  Otherwise, a simple power model (Pdyn = Coeff *
+ * Voltage^2 * Frequency) is used.
+ */
+static unsigned long
+get_dynamic_power(struct devfreq_cooling_device *dfc, unsigned long freq,
+		  unsigned long voltage)
+{
+	u64 power;
+	u32 freq_mhz;
+	struct devfreq_cooling_power *dfc_power = dfc->power_ops;
+
+	if (dfc_power->get_dynamic_power)
+		return dfc_power->get_dynamic_power(freq, voltage);
+
+	freq_mhz = freq / 1000000;
+	power = (u64)dfc_power->dyn_power_coeff * freq_mhz * voltage * voltage;
+	do_div(power, 1000000000);
+
+	return power;
+}
+
+static int devfreq_cooling_get_requested_power(struct thermal_cooling_device *cdev,
+					       struct thermal_zone_device *tz,
+					       u32 *power)
+{
+	struct devfreq_cooling_device *dfc = cdev->devdata;
+	struct devfreq *df = dfc->devfreq;
+	struct devfreq_dev_status *status = &df->last_status;
+	unsigned long state;
+	unsigned long freq = status->current_frequency;
+	u32 dyn_power, static_power;
+
+	/* Get dynamic power for state */
+	state = freq_get_state(dfc, freq);
+	if (state == THERMAL_CSTATE_INVALID)
+		return -EAGAIN;
+
+	dyn_power = dfc->power_table[state];
+
+	/* Scale dynamic power for utilization */
+	dyn_power = (dyn_power * status->busy_time) / status->total_time;
+
+	/* Get static power */
+	static_power = get_static_power(dfc, freq);
+
+	trace_thermal_power_devfreq_get_power(cdev, status, freq, dyn_power,
+					      static_power);
+
+	*power = dyn_power + static_power;
+
+	return 0;
+}
+
+static int devfreq_cooling_state2power(struct thermal_cooling_device *cdev,
+				       struct thermal_zone_device *tz,
+				       unsigned long state,
+				       u32 *power)
+{
+	struct devfreq_cooling_device *dfc = cdev->devdata;
+	unsigned long freq;
+	u32 static_power;
+
+	if (state < 0 || state >= dfc->freq_table_size)
+		return -EINVAL;
+
+	freq = dfc->freq_table[state];
+	static_power = get_static_power(dfc, freq);
+
+	*power = dfc->power_table[state] + static_power;
+	return 0;
+}
+
+static int devfreq_cooling_power2state(struct thermal_cooling_device *cdev,
+				       struct thermal_zone_device *tz,
+				       u32 power, unsigned long *state)
+{
+	struct devfreq_cooling_device *dfc = cdev->devdata;
+	struct devfreq *df = dfc->devfreq;
+	struct devfreq_dev_status *status = &df->last_status;
+	unsigned long freq = status->current_frequency;
+	unsigned long busy_time;
+	s32 dyn_power;
+	u32 static_power;
+	int i;
+
+	static_power = get_static_power(dfc, freq);
+
+	dyn_power = power - static_power;
+	dyn_power = dyn_power > 0 ? dyn_power : 0;
+
+	/* Scale dynamic power for utilization */
+	busy_time = status->busy_time ?: 1;
+	dyn_power = (dyn_power * status->total_time) / busy_time;
+
+	/*
+	 * Find the first cooling state that is within the power
+	 * budget for dynamic power.
+	 */
+	for (i = 0; i < dfc->freq_table_size - 1; i++)
+		if (dyn_power >= dfc->power_table[i])
+			break;
+
+	*state = i;
+	trace_thermal_power_devfreq_limit(cdev, freq, *state, power);
+	return 0;
+}
+
+static struct thermal_cooling_device_ops devfreq_cooling_ops = {
+	.get_max_state = devfreq_cooling_get_max_state,
+	.get_cur_state = devfreq_cooling_get_cur_state,
+	.set_cur_state = devfreq_cooling_set_cur_state,
+};
+
+/**
+ * devfreq_cooling_gen_tables() - Generate power and freq tables.
+ * @dfc: Pointer to devfreq cooling device.
+ *
+ * Generate power and frequency tables: the power table hold the
+ * device's maximum power usage at each cooling state (OPP).  The
+ * static and dynamic power using the appropriate voltage and
+ * frequency for the state, is acquired from the struct
+ * devfreq_cooling_power, and summed to make the maximum power draw.
+ *
+ * The frequency table holds the frequencies in descending order.
+ * That way its indexed by cooling device state.
+ *
+ * The tables are malloced, and pointers put in dfc.  They must be
+ * freed when unregistering the devfreq cooling device.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+static int devfreq_cooling_gen_tables(struct devfreq_cooling_device *dfc)
+{
+	struct devfreq *df = dfc->devfreq;
+	struct device *dev = df->dev.parent;
+	int ret, num_opps;
+	unsigned long freq;
+	u32 *power_table = NULL;
+	u32 *freq_table;
+	int i;
+
+	num_opps = dev_pm_opp_get_opp_count(dev);
+
+	if (dfc->power_ops) {
+		power_table = kcalloc(num_opps, sizeof(*power_table),
+				      GFP_KERNEL);
+		if (!power_table)
+			return -ENOMEM;
+	}
+
+	freq_table = kcalloc(num_opps, sizeof(*freq_table),
+			     GFP_KERNEL);
+	if (!freq_table) {
+		ret = -ENOMEM;
+		goto free_power_table;
+	}
+
+	for (i = 0, freq = ULONG_MAX; i < num_opps; i++, freq--) {
+		unsigned long power_dyn, voltage;
+		struct dev_pm_opp *opp;
+
+		rcu_read_lock();
+
+		opp = dev_pm_opp_find_freq_floor(dev, &freq);
+		if (IS_ERR(opp)) {
+			rcu_read_unlock();
+			ret = PTR_ERR(opp);
+			goto free_tables;
+		}
+
+		voltage = dev_pm_opp_get_voltage(opp) / 1000; /* mV */
+
+		rcu_read_unlock();
+
+		if (dfc->power_ops) {
+			power_dyn = get_dynamic_power(dfc, freq, voltage);
+
+			dev_dbg(dev, "Dynamic power table: %lu MHz @ %lu mV: %lu = %lu mW\n",
+				freq / 1000000, voltage, power_dyn, power_dyn);
+
+			power_table[i] = power_dyn;
+		}
+
+		freq_table[i] = freq;
+	}
+
+	if (dfc->power_ops)
+		dfc->power_table = power_table;
+
+	dfc->freq_table = freq_table;
+	dfc->freq_table_size = num_opps;
+
+	return 0;
+
+free_tables:
+	kfree(freq_table);
+free_power_table:
+	kfree(power_table);
+
+	return ret;
+}
+
+/**
+ * of_devfreq_cooling_register_power() - Register devfreq cooling device,
+ *                                      with OF and power information.
+ * @np:	Pointer to OF device_node.
+ * @df:	Pointer to devfreq device.
+ * @dfc_power:	Pointer to devfreq_cooling_power.
+ *
+ * Register a devfreq cooling device.  The available OPPs must be
+ * registered on the device.
+ *
+ * If @dfc_power is provided, the cooling device is registered with the
+ * power extensions.  For the power extensions to work correctly,
+ * devfreq should use the simple_ondemand governor, other governors
+ * are not currently supported.
+ */
+struct thermal_cooling_device *
+of_devfreq_cooling_register_power(struct device_node *np, struct devfreq *df,
+				  struct devfreq_cooling_power *dfc_power)
+{
+	struct thermal_cooling_device *cdev;
+	struct devfreq_cooling_device *dfc;
+	char dev_name[THERMAL_NAME_LENGTH];
+	int err;
+
+	dfc = kzalloc(sizeof(*dfc), GFP_KERNEL);
+	if (!dfc)
+		return ERR_PTR(-ENOMEM);
+
+	dfc->devfreq = df;
+
+	if (dfc_power) {
+		dfc->power_ops = dfc_power;
+
+		devfreq_cooling_ops.get_requested_power =
+			devfreq_cooling_get_requested_power;
+		devfreq_cooling_ops.state2power = devfreq_cooling_state2power;
+		devfreq_cooling_ops.power2state = devfreq_cooling_power2state;
+	}
+
+	err = devfreq_cooling_gen_tables(dfc);
+	if (err)
+		goto free_dfc;
+
+	err = get_idr(&devfreq_idr, &dfc->id);
+	if (err)
+		goto free_tables;
+
+	snprintf(dev_name, sizeof(dev_name), "thermal-devfreq-%d", dfc->id);
+
+	cdev = thermal_of_cooling_device_register(np, dev_name, dfc,
+						  &devfreq_cooling_ops);
+	if (IS_ERR(cdev)) {
+		err = PTR_ERR(cdev);
+		dev_err(df->dev.parent,
+			"Failed to register devfreq cooling device (%d)\n",
+			err);
+		goto release_idr;
+	}
+
+	dfc->cdev = cdev;
+
+	return cdev;
+